#!/bin/bash

llama-server \
  -hf deepreinforce-ai/Ornith-1.0-9B-GGUF \
  --ctx-size 65536 \
  --alias ornith-1.0 \
  --jinja \
  --chat-template-file ~/.config/llama.cpp/ornith-toolfix.jinja \
  -ngl 99 \
  -fa on \
  -b 2048 \
  -ub 1024 \
  --cache-ram 2048 \
  --kv-unified \
  --cache-type-k q8_0 \
  --cache-type-v q8_0 \
  --presence-penalty 1.5 \
  --repeat-penalty 1.15 \
  --host 0.0.0.0